learning_rate: 5e-5

num_epochs: 1

total_batch_size: 16

Downloads last month
3
Safetensors
Model size
331M params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lblaoke/opt-350m-hh-rlhf-dpo-trl-v5

Base model

facebook/opt-350m
Finetuned
(1)
this model

Dataset used to train lblaoke/opt-350m-hh-rlhf-dpo-trl-v5

Collection including lblaoke/opt-350m-hh-rlhf-dpo-trl-v5